An e-commerce data analysis processing method, system and storage medium

Abstract

This invention provides an e-commerce data analysis and processing method, system, and storage medium, belonging to the field of data processing technology. Specifically, it includes: determining product change profiles within user profiles based on changes in products corresponding to different user profiles and historical purchase data of matching users; obtaining recommended browsing data of matching users for product change profiles; determining, based on the recommended browsing data of different matching users, when the risk coefficient of user profile changes for matching users of product change profiles meets requirements; determining the association between historical purchase data of matching users of product change profiles and different product change profiles; and, combined with the changes in products corresponding to different product change profiles, determining an update processing strategy for the user profiles of matching users, thereby improving the timeliness of user profile update processing on e-commerce platforms.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to an e-commerce data analysis and processing method, system and storage medium. Background Technology

[0002] When recommending products to users, e-commerce platforms often analyze and process users' historical purchase data to make targeted product recommendations. Specifically, the invention patent application CN202111655687.9, "E-commerce Cloud Data Analysis Method and System," generates a sentiment quantification matrix from the shopping and review data of the analyzed object, thereby accurately recommending products that the analyzed object is inclined to purchase. However, the following technical problems exist:

[0003] Existing technical solutions neglect changes in the products listed on e-commerce platforms when updating user profiles. Specifically, when there are many changes in the products listed on e-commerce platforms, if user profiles are not updated in a targeted manner, the accuracy of the recommendation process for newly listed products may be affected.

[0004] To address the aforementioned technical problems, this application provides an e-commerce data analysis and processing method, system, and storage medium. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted:

[0006] Specifically, in the first aspect, this application provides an e-commerce data analysis and processing method, which specifically includes:

[0007] S1 determines the newly listed products on the e-commerce platform, and based on the changes in the newly listed products corresponding to different user profiles, if it is determined that it is not necessary to update all user profiles on the e-commerce platform, proceed to the next step;

[0008] S2 determines the product change profile in the user profile based on the changes in products corresponding to different user profiles and the historical purchase data of the matching user.

[0009] S3 obtains the recommended browsing data of the matching users of the product change profile. Based on the recommended browsing data of different matching users, when the change risk coefficient of the user profile of the matching user of the product change profile meets the requirements, proceed to the next step.

[0010] S4 determines the association between the historical purchase data of the matching user of the product change profile and different product change profiles, and determines the update processing strategy of the user profile of the matching user by combining the changes of the products corresponding to different product change profiles.

[0011] The beneficial effects of this invention are as follows:

[0012] By analyzing the changes in newly listed products corresponding to different user profiles, it is determined whether a complete update of the user profiles of the e-commerce platform is required. This enables the determination of the update requirements for the e-commerce platform's user profiles based on the number of newly listed products for different user profiles and their changes compared to the original products. This avoids the impact of inaccurate user profiles on the accuracy of the recommendation process for newly listed products on the e-commerce platform, and ensures the real-time nature of user profile update processing.

[0013] By using the historical purchase data of matching users with product change profiles to determine the correlation with different product change profiles, and combining the changes in products corresponding to different product change profiles, the update processing strategy for matching user profiles is determined. This enables the determination of the correlation between matching users and different product change profiles from the perspective of historical purchase data, and further combines the changes in products corresponding to product change profiles with different degrees of correlation to achieve the filtering of matching users with high update needs, thereby improving the efficiency of update processing and the real-time nature of user profiles.

[0014] A further technical solution is that the newly listed products are products that have been newly added to the e-commerce platform within the most recent preset time period.

[0015] A further technical solution is that the user profile includes students, newlyweds, and mothers and infants.

[0016] A further technical solution is that the changes in the newly listed products corresponding to the user profile include the number of newly listed products corresponding to the user profile and the changes in the number of different newly listed products compared to the original number of products.

[0017] A further technical solution involves determining that a complete update of the user profiles on the e-commerce platform is unnecessary, specifically including:

[0018] Based on the changes in newly listed products corresponding to different user profiles, determine the ratio of the number of newly listed products to the number of existing products for each user profile, and use this ratio as the product change coefficient.

[0019] Based on the product variation coefficient of different user profiles, the variable user profiles in the user profiles are determined;

[0020] Based on the proportion of users with the changed user profiles in the e-commerce platform, it is determined whether a complete update of the user profiles of the e-commerce platform is required.

[0021] A further technical solution is that the variable user profile is a user profile whose product change coefficient is greater than a preset change coefficient threshold.

[0022] A further technical solution is that when the proportion of the number of users with the changed user profiles in the e-commerce platform is within a preset range of user proportions, it is determined that a complete update of the user profiles of the e-commerce platform is required.

[0023] A further technical solution is that the method for determining the update processing strategy for the user profile matching the user is as follows:

[0024] The proportion of the number of historical purchases of the matched user in different product change profiles is determined based on the historical purchase data of the matched user. Based on the proportion, the purchase correlation coefficient between the matched user and different product change profiles is determined.

[0025] Based on the changes in products corresponding to different product change profiles, determine the sum of the number of newly listed products and the number of previously delisted products corresponding to different product change profiles, and use this sum as the number of changed products.

[0026] The associated change profile of the matched user is determined based on the purchase correlation coefficient with different product change profiles. The update processing strategy for the user profile of the matched user is determined based on the sum of the number of change products of different associated change profiles.

[0027] A further technical aspect is that the associated change profile is a product change profile where the purchase correlation coefficient with the matched user is greater than a preset purchase correlation coefficient threshold.

[0028] A further technical solution involves determining an update strategy for the user profile of the matched user based on the sum of the number of changed items in different associated change profiles, specifically including:

[0029] When the sum of the number of changed products in different associated changed profiles is greater than the preset threshold for the number of changed products, the update processing strategy for the user profile of the matching user is determined to be to update the user profile of the matching user.

[0030] When the sum of the number of changed products in different related change profiles is not greater than a preset threshold for the number of changed products, it is determined whether the sum of the number of changed products in different related change profiles is within a preset range for the number of changed products. If so, the update processing strategy for the user profile of the matched user is determined to be to use the e-commerce platform usage data of the matched user in a preset period of time in the future to determine whether the user profile of the matched user needs to be updated. If not, it is determined that the user profile of the matched user does not need to be updated.

[0031] Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described e-commerce data analysis and processing method when running the computer program.

[0032] Thirdly, the present invention provides a computer storage medium storing a computer program thereon, which, when executed in a computer, causes the computer to perform the aforementioned e-commerce data analysis and processing method.

[0033] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0034] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0035] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0036] Figure 1 This is a flowchart of an e-commerce data analysis and processing method;

[0037] Figure 2 This is a flowchart that determines whether a complete update of the user profile on the e-commerce platform is unnecessary.

[0038] Figure 3 This is a flowchart illustrating the method for determining the product change profile in the user profile;

[0039] Figure 4 This is a flowchart illustrating the method for determining the risk coefficient of changes in user profiles that match product change profiles.

[0040] Figure 5 It is a framework diagram of a computer system. Detailed Implementation

[0041] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0042] In this application, by analyzing changes in the products listed on the e-commerce platform, the number of newly listed products, and the data on the removal of existing products, the user profile update strategy on the e-commerce platform is dynamically adjusted accordingly, thereby ensuring the timeliness of user profile updates when changes occur in the listed products.

[0043] Example 1

[0044] like Figure 1 As shown, this application provides an e-commerce data analysis and processing method, specifically including:

[0045] S1 determines the newly listed products on the e-commerce platform, and based on the changes in the newly listed products corresponding to different user profiles, if it is determined that it is not necessary to update all user profiles on the e-commerce platform, proceed to the next step;

[0046] S2 determines the product change profile in the user profile based on the changes in products corresponding to different user profiles and the historical purchase data of the matching user.

[0047] S3 obtains the recommended browsing data of the matching users of the product change profile. Based on the recommended browsing data of different matching users, when the change risk coefficient of the user profile of the matching user of the product change profile meets the requirements, proceed to the next step.

[0048] S4 determines the association between the historical purchase data of the matching user of the product change profile and different product change profiles, and determines the update processing strategy of the user profile of the matching user by combining the changes of the products corresponding to different product change profiles.

[0049] Furthermore, the newly listed products are those that have recently been added to the e-commerce platform within a preset time period.

[0050] Specifically, the user profiles include student groups, newlywed groups, and mothers and infants.

[0051] Specifically, the changes in newly listed products corresponding to the user profile include the number of newly listed products corresponding to the user profile and the changes in the number of different newly listed products compared to the original number of products.

[0052] It should be noted that, as Figure 2 As shown, it has been determined that a complete update of the user profiles for the e-commerce platform is not required, specifically including:

[0053] Based on the changes in newly listed products corresponding to different user profiles, determine the ratio of the number of newly listed products to the number of existing products for each user profile, and use this ratio as the product change coefficient.

[0054] Based on the product variation coefficient of different user profiles, the variable user profiles in the user profiles are determined;

[0055] Based on the proportion of users with the changed user profiles in the e-commerce platform, it is determined whether a complete update of the user profiles of the e-commerce platform is required.

[0056] Furthermore, the variable user profile is a user profile whose product change coefficient is greater than a preset change coefficient threshold.

[0057] It is understandable that when the proportion of users with changed user profiles in the e-commerce platform is within a preset user proportion range, it is determined that a complete update of the user profiles of the e-commerce platform is required.

[0058] In another possible embodiment, determining that a complete update of the user profiles for the e-commerce platform is not required specifically includes:

[0059] Based on the changes in newly listed products corresponding to different user profiles, determine the ratio of the number of newly listed products to the number of existing products for each user profile, and use this ratio as the product change coefficient.

[0060] The average coefficient of variation is determined based on the average value of the product variation coefficients for different user profiles.

[0061] Based on the average variation coefficient, determine whether a complete update of the user profiles of the e-commerce platform is required.

[0062] Furthermore, when the average variation coefficient is greater than a preset average coefficient threshold, it is determined that a complete update of the user profile of the e-commerce platform is required.

[0063] Optionally, it can be determined that a complete update of the user profiles for the e-commerce platform is not required, specifically including:

[0064] The number of newly listed products on the e-commerce platform is obtained. When the number of newly listed products on the e-commerce platform exceeds a preset threshold for the number of listed products, it is determined that a complete update of the user profile of the e-commerce platform is required.

[0065] When the number of newly listed products on the e-commerce platform is not greater than a preset threshold for the number of listed products:

[0066] Based on the number of newly listed products and the original number of products on the e-commerce platform, the change impact factor of the e-commerce platform is determined. When the change impact factor is within the preset change impact factor range, it is determined that there is no need to perform a full update of the user profile of the e-commerce platform.

[0067] When the change influencing factor is not within the preset change influencing factor range:

[0068] Based on the changes in newly listed products corresponding to different user profiles, the ratio of the number of newly listed products to the number of existing products corresponding to different user profiles is determined and used as the product change coefficient. When the product change coefficients for different user profiles are all less than the preset product change coefficient threshold, it is determined that there is no need to perform a full update of the user profiles of the e-commerce platform.

[0069] When there is a user profile for which the product variation coefficient is not less than the preset product variation coefficient threshold:

[0070] Based on the average value of the product variation coefficients of different user profiles, the average variation coefficient is determined. When the average variation coefficient is greater than the preset average coefficient threshold, it is determined that the user profiles of the e-commerce platform need to be updated.

[0071] When the average coefficient of variation is not greater than the preset average coefficient threshold:

[0072] The user profiles with product change coefficients greater than a preset change coefficient threshold are obtained and used as the changed user profiles in the user profiles. When the proportion of users in the changed user profiles in the e-commerce platform does not meet the requirements, it is determined that the entire user profile of the e-commerce platform needs to be updated.

[0073] When the proportion of users with the modified user profile in the e-commerce platform meets the requirements:

[0074] Based on the number of newly listed products and the product change coefficient for different user profiles, and combined with the number of users for different user profiles, the change impact coefficient for different user profiles is determined. When there are user profiles whose change impact coefficient does not meet the requirements, it is determined that all user profiles of the e-commerce platform need to be updated.

[0075] When there is no user profile whose change impact coefficient does not meet the requirements:

[0076] Based on the impact coefficients of changes in different user profiles, the impact value of platform changes on the e-commerce platform is determined, and the impact value of platform changes is used to determine whether a complete update of the user profiles of the e-commerce platform is required.

[0077] Furthermore, if the impact value of the platform change is not within the preset impact value range, then it is indeed necessary to perform a complete update of the user profile of the e-commerce platform.

[0078] Specifically, the preset commodity variation coefficient threshold is less than the preset variation coefficient threshold.

[0079] It should be noted that the changes in the products corresponding to the user profile include the number of newly listed products and the number of previously delisted products.

[0080] It is understood that the historical purchase data of the matched user refers to the number of historical purchases made by the matched user in the user profile.

[0081] Specifically, such as Figure 3 As shown, the method for determining the product change profile in the user profile is as follows:

[0082] Based on the changes in the products corresponding to the user profile, determine the number of newly listed products and the number of previously delisted products corresponding to the user profile. Determine the listing change coefficient based on the ratio of the number of newly listed products to the number of previously listed products, and determine the delisting change coefficient based on the ratio of the number of previously delisted products to the number of previously listed products.

[0083] Based on the historical purchase data of the matching users of the user profile, determine the historical purchase count of the matching users of the user profile, and determine the matching hot users of the user profile based on the historical purchase count.

[0084] Based on the listing change coefficient, the delisting change coefficient, and the number of users matching the popularity, the profile change risk value of the user profile is determined, and the profile change risk value is used to determine whether the user profile is a product change profile.

[0085] Furthermore, the matched users are those whose historical purchase count exceeds a preset purchase count threshold.

[0086] It should also be noted that the risk value of the user profile change is determined by multiplying the listing change coefficient, the delisting change coefficient and the number of users with matching popularity.

[0087] Specifically, when the risk value of the user profile change is greater than the preset risk threshold, the user profile is determined to be a product change profile.

[0088] It is understandable that when the user profile does not belong to the product change profile, the matching user corresponding to the user profile does not need to undergo user profile update processing.

[0089] Optionally, the method for determining the product change profile in the user profile is as follows:

[0090] Based on the changes in the products corresponding to the user profile, determine the number of newly listed products and the number of previously delisted products corresponding to the user profile. Determine the listing change coefficient based on the ratio of the number of newly listed products to the number of previously listed products, and determine the delisting change coefficient based on the ratio of the number of previously delisted products to the number of previously listed products.

[0091] Based on the historical purchase data of the users matched by the user profile, the number of users matched by the user profile is determined, and based on the proportion of the number of users matched by the user profile in the e-commerce platform, the proportion of matched users is determined.

[0092] Based on the average of the listing change coefficient, the delisting change coefficient and the matching user ratio, the profile change risk value of the user profile is determined, and the profile change risk value is used to determine whether the user profile is a product change profile.

[0093] In another possible embodiment, the method for determining the product change profile in the user profile is as follows:

[0094] Based on the changes in the products corresponding to the user profile, determine the number of newly listed products and the number of previously delisted products corresponding to the user profile. Determine the listing change coefficient based on the ratio of the number of newly listed products to the number of previously listed products, and determine the delisting change coefficient based on the ratio of the number of previously delisted products to the number of previously listed products. If the sum of the listing change coefficient and the delisting change coefficient does not meet the requirements, then the user profile is determined to be a product change profile.

[0095] When the sum of the put-on and take-off variation coefficients meets the requirements:

[0096] The number of newly listed products and the number of previously delisted products are obtained. If the sum of the number of newly listed products and the number of previously delisted products is less than a preset threshold for the number of changed products, then the user profile is determined not to belong to the product change profile.

[0097] When the sum of the number of newly listed products and the number of previously delisted products is not less than a preset threshold for the number of products to be changed:

[0098] Based on the historical purchase data of the users matched by the user profile, the number of users matched by the user profile is determined. Based on the proportion of the number of users matched by the user profile in the e-commerce platform, the proportion of matched users is determined. When the proportion of matched users is greater than a preset threshold for the proportion of matched users, the user profile is determined to belong to the product change profile.

[0099] When the proportion of matched users is not greater than the preset threshold for the proportion of matched users:

[0100] Based on the historical purchase data of the matching users of the user profile, the historical purchase count of the matching users of the user profile is determined, and the matching hot users of the user profile are determined according to the historical purchase count. When the number of matching hot users is greater than the preset hot user count threshold, the user profile is determined to belong to the product change profile.

[0101] When the number of matched popular users is not greater than a preset threshold for the number of popular users:

[0102] Based on the listing change coefficient, the delisting change coefficient, and the number of users matching the popularity, the profile change risk value of the user profile is determined, and the profile change risk value is used to determine whether the user profile is a product change profile.

[0103] Furthermore, the recommended browsing data for the matched user includes recommended products from the e-commerce platform of the matched user and the browsing data of the recommended products.

[0104] Specifically, such as Figure 4 As shown, the method for determining the risk coefficient of change in the user profile of the user matching the product change profile is as follows:

[0105] Based on the recommended browsing data of different matching users, the recommended products of the e-commerce platform of the matching users of the product change profile are determined, as well as the browsing data of the matching users on the recommended products;

[0106] Based on the proportion of unviewed recommended products among the recommended products, a recommendation deviation coefficient is determined for different matching users;

[0107] The change risk coefficient of the user profile of the matching user is determined based on the average value of the recommendation deviation coefficient of different matching users.

[0108] Furthermore, the change risk coefficient of the user profile of the matching user in the product change profile ranges from 0 to 1. When the change risk coefficient of the matching user's user profile is greater than the preset change risk coefficient threshold, it is determined that the change risk coefficient of the matching user's user profile in the product change profile does not meet the requirements.

[0109] It is understandable that when the risk coefficient of the user profile of the matching user of the product change profile does not meet the requirements, the user profiles of all matching users of the product change profile will be updated.

[0110] Specifically, the method for determining the update strategy for the user profile matching the user is as follows:

[0111] The proportion of the number of historical purchases of the matched user in different product change profiles is determined based on the historical purchase data of the matched user. Based on the proportion, the purchase correlation coefficient between the matched user and different product change profiles is determined.

[0112] Based on the changes in products corresponding to different product change profiles, determine the sum of the number of newly listed products and the number of previously delisted products corresponding to different product change profiles, and use this sum as the number of changed products.

[0113] The associated change profile of the matched user is determined based on the purchase correlation coefficient with different product change profiles. The update processing strategy for the user profile of the matched user is determined based on the sum of the number of change products of different associated change profiles.

[0114] Furthermore, the associated change profile is a product change profile where the purchase association coefficient with the matched user is greater than a preset purchase association coefficient threshold.

[0115] It should be noted that the update strategy for the user profile of the matched user is determined based on the sum of the number of changed products in different associated change profiles, specifically including:

[0116] When the sum of the number of changed products in different associated changed profiles is greater than the preset threshold for the number of changed products, the update processing strategy for the user profile of the matching user is determined to be to update the user profile of the matching user.

[0117] When the sum of the number of changed products in different related change profiles is not greater than a preset threshold for the number of changed products, it is determined whether the sum of the number of changed products in different related change profiles is within a preset range for the number of changed products. If so, the update processing strategy for the user profile of the matched user is determined to be to use the e-commerce platform usage data of the matched user in a preset period of time in the future to determine whether the user profile of the matched user needs to be updated. If not, it is determined that the user profile of the matched user does not need to be updated.

[0118] Furthermore, by utilizing the e-commerce platform usage data of the matched users within a preset future time period, it is determined whether the user profile of the matched users needs to be updated, specifically including:

[0119] If the cumulative usage time of the matched user on the e-commerce platform within a preset time period exceeds a preset time threshold, then it is determined that the user profile of the matched user needs to be updated.

[0120] If the cumulative usage time of the matched user on the e-commerce platform within a preset time period is not greater than a preset time threshold, then it is determined that there is no need to update the user profile of the matched user.

[0121] Optionally, the method for determining the update strategy for the user profile of the matched user is as follows:

[0122] S41 uses the historical purchase data of the matched user to determine the proportion of the number of historically purchased products of the matched user in different product change profiles in the total number of historically purchased products of the matched user. Based on the proportion of the number of products, the purchase correlation coefficient between the matched user and different product change profiles is determined. Based on the purchase correlation coefficient with different product change profiles, the associated change profile of the matched user is determined.

[0123] S42 determines the sum of the number of newly listed products and the number of previously delisted products corresponding to different related change profiles based on the changes in products corresponding to different related change profiles, and determines the product change factor for different related change profiles in combination with the original number of products in the related change profile.

[0124] S43 determines the profile update requirement value of the matching user's profile based on the sum of the products of the product change factors and the purchase association coefficients of different related change profiles, and uses the profile update requirement value to determine the update processing strategy of the matching user's profile.

[0125] Optionally, the update processing strategy for the user profile of the matched user is determined using the profile update requirement value, specifically including:

[0126] When the update requirement value of the user profile of the matching user is greater than the preset update requirement value threshold, the update processing strategy for the user profile of the matching user is determined to be to update the user profile of the matching user.

[0127] When the user profile update requirement value of the matched user is not greater than the preset update requirement value threshold, it is determined whether the user profile update requirement value of the matched user is within the preset update requirement value range. If so, the update processing strategy for the user profile of the matched user is determined to be to use the user's e-commerce platform usage data in the future preset time period to determine whether the user profile of the matched user needs to be updated. If not, it is determined that the user profile of the matched user does not need to be updated.

[0128] Optionally, step S41 above includes the following:

[0129] S411 uses the historical purchase data of the matched user to determine the historical purchase products of the matched user in different product change profiles. When the number of product change profiles with historical purchase products does not meet the requirements, it is determined that the user profile of the matched user needs to be updated. When the number of product change profiles with historical purchase products meets the requirements, proceed to step S412.

[0130] S412 uses the historical purchase data of the matched user to determine the proportion of the number of historically purchased products of the matched user in different product change profiles in the total number of historically purchased products of the matched user. Based on the proportion of the number of products, the purchase correlation coefficient between the matched user and different product change profiles is determined. When there is no product change profile with a purchase correlation coefficient greater than a preset purchase correlation coefficient threshold, it is determined that the user profile of the matched user does not need to be updated. When there is a product change profile with a purchase correlation coefficient greater than a preset purchase correlation coefficient threshold, proceed to step S413.

[0131] S413 takes the product change profile with purchase correlation coefficient greater than the preset purchase correlation coefficient threshold as the related change profile of the matched user. When the number of related change profiles of the matched user is greater than the preset related change profile number threshold, it is determined that the user profile of the matched user needs to be updated. When the number of related change profiles of the matched user is not greater than the preset related change profile number threshold, proceed to step S414.

[0132] S414 When the sum of the purchase correlation coefficients of different related change profiles does not meet the requirements, it is determined that the user profile of the matching user needs to be updated. When the sum of the purchase correlation coefficients of different related change profiles meets the requirements, proceed to step S42.

[0133] Optionally, step S42 above includes the following:

[0134] S421 Based on the changes in products corresponding to different related change profiles, determine the sum of the number of newly listed products and the number of previously delisted products corresponding to different related change profiles, and use this as the number of changed products. If there is a related change profile where the number of changed products does not meet the requirements, proceed to step S422. If there is no related change profile where the number of changed products does not meet the requirements, proceed to step S423.

[0135] S422 When the number of associated change profiles whose quantity of changed goods does not meet the requirements is greater than the preset threshold for the number of associated change profiles, it is determined that the user profile of the matching user needs to be updated. When the number of associated change profiles whose quantity of changed goods does not meet the requirements is not greater than the preset threshold for the number of associated change profiles, proceed to step S423.

[0136] S423 When the sum of the number of changed products in different associated change profiles does not meet the requirements, it is determined that the user profile of the matching user needs to be updated. When the sum of the number of changed products in different associated change profiles meets the requirements, proceed to step S424.

[0137] S424 determines the sum of the number of newly listed products and the number of previously delisted products corresponding to different associated change profiles, and combines this with the original number of products in the associated change profile to determine the product change factor for different associated change profiles. When the sum of the product change factors for different associated change profiles does not meet the requirements, it is determined that the user profile of the matching user needs to be updated. When the sum of the product change factors for different associated change profiles meets the requirements, proceed to step S43.

[0138] Example 2

[0139] Secondly, such as Figure 5 As shown, the present invention provides a computer system, including: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described e-commerce data analysis and processing method when running the computer program.

[0140] Example 3

[0141] Thirdly, the present invention provides a computer storage medium storing a computer program thereon, which, when executed in a computer, causes the computer to perform the aforementioned e-commerce data analysis and processing method.

[0142] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0143] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0144] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. An e-commerce data analysis processing method, characterized in that, Specifically, it includes: Once the newly listed products on the e-commerce platform are identified, and the changes in the newly listed products corresponding to different user profiles are determined, proceed to the next step if it is determined that it is not necessary to update all user profiles on the e-commerce platform. Based on the changes in products corresponding to different user profiles and the historical purchase data of matching users, the product change profile in the user profile is determined. Obtain recommended browsing data of matching users of the product change profile. Based on the recommended browsing data of different matching users, determine when the change risk coefficient of the user profile of the matching user of the product change profile meets the requirements. Use the historical purchase data of the matching user of the product change profile to determine the association with different product change profiles. Combine the change of products corresponding to different product change profiles to determine the update processing strategy of the user profile of the matching user. It has been determined that a complete update of the user profiles for the e-commerce platform is not required, specifically including: Based on the changes in newly listed products corresponding to different user profiles, determine the ratio of the number of newly listed products to the number of existing products for each user profile, and use this ratio as the product change coefficient. Based on the product variation coefficient of different user profiles, the variable user profiles in the user profiles are determined; Based on the proportion of users with the changed user profiles in the e-commerce platform, it is determined whether a complete update of the user profiles of the e-commerce platform is required.

2. The method of claim 1, wherein, The newly listed products are those that have been added to the e-commerce platform within the most recent preset time period.

3. The method of claim 1, wherein the data analysis process is performed by a plurality of servers. The changes in newly listed products corresponding to the user profile include the number of newly listed products corresponding to the user profile and the changes in the number of different newly listed products compared to the original number of products.

4. The method of claim 1, wherein the data analysis process is performed by a plurality of servers. The variable user profile refers to a user profile whose product change coefficient is greater than a preset change coefficient threshold.

5. The method of claim 1, wherein the data analysis process is performed by a plurality of servers. The method for determining the update strategy for the user profile of the matched user is as follows: The proportion of the number of historical purchases of the matched user in different product change profiles is determined based on the historical purchase data of the matched user. Based on the proportion, the purchase correlation coefficient between the matched user and different product change profiles is determined. Based on the changes in products corresponding to different product change profiles, determine the sum of the number of newly listed products and the number of previously delisted products corresponding to different product change profiles, and use this sum as the number of changed products. The associated change profile of the matched user is determined based on the purchase correlation coefficient with different product change profiles. The update processing strategy for the user profile of the matched user is determined based on the sum of the number of change products of different associated change profiles.

6. The method of claim 5, wherein the data analysis process is performed by the electronic business server. The associated change profile is a product change profile where the purchase correlation coefficient with the matched user is greater than a preset purchase correlation coefficient threshold.

7. The method of claim 5, wherein the data analysis process is performed by the server. Based on the sum of the number of changed items in different associated change profiles, the update processing strategy for the user profile of the matched user is determined, specifically including: When the sum of the number of changed products in different associated changed profiles is greater than the preset threshold for the number of changed products, the update processing strategy for the user profile of the matching user is determined to be to update the user profile of the matching user. When the sum of the number of changed products in different related change profiles is not greater than a preset threshold for the number of changed products, it is determined whether the sum of the number of changed products in different related change profiles is within a preset range for the number of changed products. If so, the update processing strategy for the user profile of the matched user is determined to be to use the e-commerce platform usage data of the matched user in a preset period of time in the future to determine whether the user profile of the matched user needs to be updated. If not, it is determined that the user profile of the matched user does not need to be updated.

8. A computer system, comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes an e-commerce data analysis and processing method according to any one of claims 1-7.

9. A computer storage medium storing a computer program thereon, wherein when the computer program is executed in a computer, the computer executes the e-commerce data analysis and processing method according to any one of claims 1-7.

Images